Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 497 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0004

Data Index: 638117 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0841. Min Act: -0.0003

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0855. Min Act: -0.0004

Data Index: 1333471 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0830. Min Act: -0.0003

Data Index: 61990 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0831. Min Act: -0.0003

Data Index: 87270 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0813. Min Act: -0.0003

Data Index: 127556 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1355062 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0793. Min Act: -0.0003

Data Index: 623094 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1263097 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0782. Min Act: -0.0003

Data Index: 596442 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0770. Min Act: -0.0004

Data Index: 1013579 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0763. Min Act: -0.0003

Data Index: 461399 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0800. Min Act: -0.0003

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0762. Min Act: -0.0004

Data Index: 900685 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0742. Min Act: -0.0003

Data Index: 787171 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0747. Min Act: -0.0003

Data Index: 612042 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0732. Min Act: -0.0003

Data Index: 639056 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0695. Min Act: -0.0003

Data Index: 67099 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1291436 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0732. Min Act: -0.0003

Data Index: 176839 (C4 (Web Text))

Max Activating Token Index: 1019